@inproceedings{mao-etal-2024-rafe,
title = "{R}a{F}e: Ranking Feedback Improves Query Rewriting for {RAG}",
author = "Mao, Shengyu and
Jiang, Yong and
Chen, Boli and
Li, Xiao and
Wang, Peng and
Wang, Xinyu and
Xie, Pengjun and
Huang, Fei and
Chen, Huajun and
Zhang, Ningyu",
editor = "Al-Onaizan, Yaser and
Bansal, Mohit and
Chen, Yun-Nung",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-emnlp.49",
doi = "10.18653/v1/2024.findings-emnlp.49",
pages = "884--901",
abstract = "As Large Language Models (LLMs) and Retrieval Augmentation Generation (RAG) techniques have evolved, query rewriting has been widely incorporated into the RAG system for downstream tasks like open-domain QA to enhance document retrieval by reformulating queries. Many works have attempted to improve query rewriting in smaller models to avoid rewriting with costly LLMs, and the most common method is to employ reinforcement learning for feedback training. However, current methods require annotations (labeled relevant documents or downstream answers) or predesigned rewards for feedback, lack generalization, and fail to utilize signals tailored for query rewriting. In this paper, we propose RaFe, a framework for training query rewriting models. By leveraging reranker, RaFe provides ranking feedback aligned well with the rewriting objectives without needing signals from annotations and supports both online and offline training models. Experimental results demonstrate that with a general and publicly available reranker, RaFe can effectively steer the training for rewrite models.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mao-etal-2024-rafe">
<titleInfo>
<title>RaFe: Ranking Feedback Improves Query Rewriting for RAG</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shengyu</namePart>
<namePart type="family">Mao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yong</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Boli</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiao</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peng</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xinyu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pengjun</namePart>
<namePart type="family">Xie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fei</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Huajun</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ningyu</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yaser</namePart>
<namePart type="family">Al-Onaizan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, Florida, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>As Large Language Models (LLMs) and Retrieval Augmentation Generation (RAG) techniques have evolved, query rewriting has been widely incorporated into the RAG system for downstream tasks like open-domain QA to enhance document retrieval by reformulating queries. Many works have attempted to improve query rewriting in smaller models to avoid rewriting with costly LLMs, and the most common method is to employ reinforcement learning for feedback training. However, current methods require annotations (labeled relevant documents or downstream answers) or predesigned rewards for feedback, lack generalization, and fail to utilize signals tailored for query rewriting. In this paper, we propose RaFe, a framework for training query rewriting models. By leveraging reranker, RaFe provides ranking feedback aligned well with the rewriting objectives without needing signals from annotations and supports both online and offline training models. Experimental results demonstrate that with a general and publicly available reranker, RaFe can effectively steer the training for rewrite models.</abstract>
<identifier type="citekey">mao-etal-2024-rafe</identifier>
<identifier type="doi">10.18653/v1/2024.findings-emnlp.49</identifier>
<location>
<url>https://aclanthology.org/2024.findings-emnlp.49</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>884</start>
<end>901</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T RaFe: Ranking Feedback Improves Query Rewriting for RAG
%A Mao, Shengyu
%A Jiang, Yong
%A Chen, Boli
%A Li, Xiao
%A Wang, Peng
%A Wang, Xinyu
%A Xie, Pengjun
%A Huang, Fei
%A Chen, Huajun
%A Zhang, Ningyu
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Findings of the Association for Computational Linguistics: EMNLP 2024
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F mao-etal-2024-rafe
%X As Large Language Models (LLMs) and Retrieval Augmentation Generation (RAG) techniques have evolved, query rewriting has been widely incorporated into the RAG system for downstream tasks like open-domain QA to enhance document retrieval by reformulating queries. Many works have attempted to improve query rewriting in smaller models to avoid rewriting with costly LLMs, and the most common method is to employ reinforcement learning for feedback training. However, current methods require annotations (labeled relevant documents or downstream answers) or predesigned rewards for feedback, lack generalization, and fail to utilize signals tailored for query rewriting. In this paper, we propose RaFe, a framework for training query rewriting models. By leveraging reranker, RaFe provides ranking feedback aligned well with the rewriting objectives without needing signals from annotations and supports both online and offline training models. Experimental results demonstrate that with a general and publicly available reranker, RaFe can effectively steer the training for rewrite models.
%R 10.18653/v1/2024.findings-emnlp.49
%U https://aclanthology.org/2024.findings-emnlp.49
%U https://doi.org/10.18653/v1/2024.findings-emnlp.49
%P 884-901
Markdown (Informal)
[RaFe: Ranking Feedback Improves Query Rewriting for RAG](https://aclanthology.org/2024.findings-emnlp.49) (Mao et al., Findings 2024)
ACL
- Shengyu Mao, Yong Jiang, Boli Chen, Xiao Li, Peng Wang, Xinyu Wang, Pengjun Xie, Fei Huang, Huajun Chen, and Ningyu Zhang. 2024. RaFe: Ranking Feedback Improves Query Rewriting for RAG. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 884–901, Miami, Florida, USA. Association for Computational Linguistics.